Alibaba/Qwen

Latest AI news, models and releases from Alibaba/Qwen. ['CodeQwen1.5', 'Cotype Light 3', 'Cotype Pro 3', 'Fun-Realtime-TTS', 'Hanguang', 'Hanguang 800', 'HappyOyster 1.0', 'ICN Switch 1.0', 'not specified', 'Panjiu', 'Qianwen', 'Qoder Security', 'QVQ-72B-Preview', 'QVQ-Max', 'Qwen', 'Qwen 2', 'Qwen2.5', 'Qwen2.5-14B-Instruct-1M', 'Qwen2.5-32B', 'Qwen-2.5 72B', 'Qwen2.5-7B', 'Qwen2.5-7B-Instruct-1M', 'Qwen2.5-Coder', 'Qwen2.5-Coder-0.5B', 'Qwen2.5-Coder-0.5B-Instruct', 'Qwen2.5-Coder-14B', 'Qwen2.5-Coder-1.5B', 'Qwen2.5-Coder-1.5B-Instruct', 'Qwen2.5-Coder-32B', 'Qwen2.5-Coder-32B-Instruct', 'Qwen2.5-Coder-3B', 'Qwen2.5-Coder-3B-Instruct', 'Qwen2.5-Coder-7B', 'Qwen2.5-Coder-7B-Instruct', 'Qwen2.5-Coder-Instruct', 'Qwen2.5-Math-1.5B', 'Qwen2.5-Math-1.5B-Instruct', 'Qwen2.5-Math-72B', 'Qwen2.5-Math-72B-Instruct', 'Qwen2.5-Math-7B']

Models 🇨🇳

Qwen2.5 Omni: Sees, Hears, Speaks, Writes — All in One

Alibaba Qwen has released Qwen2.5-Omni, a new flagship multimodal model capable of processing text, images, audio, and video, as well as generating responses in text and natural speech in real time. The model, built on a Thinker-Talker architecture, is open-source and demonstrates high performance across all modalities.

Alibaba/QwenAlibaba/Qwen
Alibaba Qwen28.07 · 00:03
Models 🇨🇳

Alibaba Qwen Releases QVQ-Max: Visual Reasoning Model with Evidence

Alibaba Qwen has officially released QVQ-Max, the first version of its visual reasoning model. It can not only recognize images and videos but also analyze them, solving tasks from mathematics to creativity. The developers noted that the model's accuracy on the MathVision benchmark increases with the length of the thinking process.

Alibaba/QwenAlibaba/Qwen
Alibaba Qwen28.07 · 00:03
Fresh news